Return factual address risk signals: entity label/category, source count, bounded behavioral flags, coarse risk_indicator, and an informational-only disclaimer. This is not AML/KYT/compliance advice.
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| data | No | ||
| error | No | ||
| endpoint | Yes | ||
| status_code | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It does disclose the informational nature, bounded flags, coarse risk indicator, and non-advice caveat. However, it does not explicitly state whether the operation is read-only, mention data freshness, or address any side effects, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and output components, and ends with an essential disclaimer. Every sentence contributes value with no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values are likely detailed there. The description adds context about output categories and limitations. However, it lacks usage guidance and parameter specifics, making it only partially complete for a tool with one parameter and no annotation support.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter, 'address', has no description in the schema (0% coverage) and the tool description adds no additional meaning beyond the parameter name. It does not specify accepted address formats, networks, or examples, so the agent gains no extra semantic information from the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns factual address risk signals and lists specific output components (entity label/category, source count, bounded behavioral flags, coarse risk_indicator, disclaimer). This distinguishes it from siblings like risk_check by emphasizing 'coarse' and 'factual' outputs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a legal disclaimer ('not AML/KYT/compliance advice') but gives no explicit guidance on when to use this tool versus alternatives like risk_check or address_intelligence. There is no mention of appropriate use cases or exclusions beyond the disclaimer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tool clusters have unclear boundaries: address_evidence_pack, address_intelligence, address_risk, risk_check, wallet_detail, wallet_summary, and wallet_trust_safety all return address-related intelligence with subtle differences. Similarly, pulse_dormant, chain_awakenings, and dormancy_flushes all describe dormant-coin reactivation events, and whale_alerts overlaps heavily with pulse_whales. Agents will likely struggle to select the correct tool without deep domain knowledge.
Tool names predominantly follow a snake_case convention with domain-prefix patterns (address_*, batch_*, entity_*, mempool_*, pulse_*, timestamp_*, tx_*, wallet_*). There are minor deviations like op_return_decode (object-verb ordering) and some noun-only names, but overall the pattern is predictable and readable.
With 44 tools, this is a large surface that exceeds the 'too many' threshold in the calibration scale. While the server covers a broad Bitcoin intelligence domain, the sheer number of tools—especially with overlapping functionality—makes it feel bloated and difficult to navigate.
The tool set covers virtually every major aspect of Bitcoin intelligence: address analysis, entity rollups, mempool state, network stats, mining pools, on-chain pulse events, transaction verification, timestamping, and batch operations. There are no obvious dead ends or missing capabilities for the stated purpose.